Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description goes well beyond the annotations by disclosing the specific fail mode (PaymentRequired document when _meta['x402/payment'] is missing), the asynchronous settlement behavior, and the successful return value (orderKey). This is rich behavioral context for a paid mutation operation and gives the agent precise expectations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences and front-loads the essential paid-over-x402 context before the operational details. It is somewhat dense, but every sentence earns its place by covering payment, error condition, success path, and next step.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the operation has no output schema and involves payment plus async settlement, the description covers the main flow well: required payment metadata, PaymentRequired error document, async validation, orderKey return, and collection via sibling. It does not describe exact error payloads beyond isError or validation-failure details, but remains sufficiently complete for an agent to invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3: targetAddress and language are fully documented with types, regex, and enum values. The description does not add parameter-level semantics, but it does clarify the external payment metadata requirement, which is not an input property.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action: buying a flash audit via x402 payment in USDC on Base, and the expected result: an orderKey to use with collect_flash_audit. It distinguishes this tool from its sibling by explicitly linking to collect_flash_audit and the paid nature of the operation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains the payment condition and the follow-up step ('returns an orderKey to collect with collect_flash_audit'), but it does not explicitly compare this tool to check_contract_free or flash_audit_terms. Usage context is implied by the paid/x402 framing, but exclusions and alternative conditions are left to the agent to infer.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.